© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 109263
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĸ¯å¡Ķ
    -0.31
    èģ¿
    -0.30
    alars
    -0.28
    çű
    -0.25
    ób
    -0.24
    èīĩ
    -0.24
     Ãĸzel
    -0.24
    .synthetic
    -0.24
    åIJ¦
    -0.24
     [...]
    -0.24
    POSITIVE LOGITS
     Pass
    0.29
    éķĽ
    0.28
    æĪª
    0.28
    éĩĩ
    0.28
    åħ³
    0.27
    @email
    0.27
    tn
    0.26
     half
    0.25
    ç´§å¯Ĩç»ĵåIJĪ
    0.25
    sher
    0.25
    Activations Density 0.072%

    No Known Activations

    This feature has no known activations.